Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3116 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1445590 (Python Code)

Max Activating Token Index: 707

Text #1

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1650365 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1396525 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1552135 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1422433 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1380459 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0597. Min Act: -0.0000

Data Index: 1498416 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1449192 (Python Code)

Max Activating Token Index: 537

Text #8

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1384428 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1464895 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1458853 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1634758 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1642674 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1386016 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1586139 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1551357 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1436776 (Python Code)

Max Activating Token Index: 524

Text #17

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1645939 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1454101 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 1.2618. Min Range: -1.2618

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1557849 (Python Code)

Max Activating Token Index: 350